Exploring MCP Server Console

  • Release version: Australia
  • Updated August 8, 2025
  • 3 minutes to read
    • Summarize
    Summarized using AI
    This content was generated using new OpenAI-powered functionality. Results are provided on an as is basis and are not guaranteed to be accurate or complete.

    Summary of Exploring MCP Server Console

    The Model Context Protocol (MCP) Server Console enables ServiceNow customers to create and manage MCP servers that facilitate communication between AI applications (MCP clients) and ServiceNow instances. MCP servers expose tools—defined functionalities and data—that AI clients can access to retrieve information or perform actions on the instance securely using OAuth 2.0 authentication. This capability allows integration with various AI applications such as Microsoft Copilot or Claude, enhancing automation and data accessibility within ServiceNow workflows.

    Show full answer Show less

    Key Features

    • Creation and Configuration of MCP Servers: AI administrators can create MCP servers and define which tools (functional capabilities) to expose to AI clients.
    • Tool Management: Tools can be created based on existing ServiceNow capabilities like Now Assist skills, and customized to expose specific fields and actions.
    • OAuth Inbound Integrations: Secure access to MCP servers is enforced by creating OAuth inbound integrations for each AI client.
    • Preconfigured Quickstart Server: MCP Server Console provides a Quickstart Server with sample tools for incident and case record lookup and summarization, facilitating quick onboarding and testing.
    • Multi-instance Access: Using the ServiceNow Model Context Protocol Client, AI applications on one instance can access MCP servers on another instance, enabling cross-instance integrations.
    • Monitoring: AI Gateway in AI Control Tower allows administrators to monitor MCP server access and view usage metrics.

    Key Outcomes

    • Standardized AI Integration: MCP Server Console standardizes how AI applications communicate with ServiceNow instances, enabling consistent and scalable AI-driven automation.
    • Enhanced Security: OAuth 2.0 authentication ensures secure and controlled access for AI clients to sensitive instance data and functions.
    • Customizable Toolsets: Administrators can tailor the exposed functionalities to different use cases (e.g., HR, IT) and client requirements.
    • Improved Employee Experience: Employees can interact with AI clients that leverage MCP servers to quickly get summaries or perform actions on incidents and cases, streamlining workflows.

    Practical Steps for Customers

    • Identify the instance functionalities to expose to AI clients.
    • Use the Quickstart Server for initial exploration or create custom MCP servers and tools as needed.
    • Create OAuth inbound integrations to secure AI client connections.
    • Configure AI clients with server and authentication details to enable communication.
    • Leverage AI Gateway to monitor MCP server usage and performance metrics.

    Learn about how you can use Model Context Protocol (MCP) servers to allow AI applications to access data and perform actions on a ServiceNow instance.

    MCP Server Console overview

    The Model Context Protocol defines a standard method of communication between large language models (LLMs) and external systems, such as a ServiceNow instance. AI applications connect to an external system from an MCP client, such as an AI agent, using an MCP server. The server tells the client which external resources it can access and how to access them. Then, from an MCP client, users can request information from the server and automate functionality using the available tools and data that the server returns. For general information about the Model Context Protocol and MCP terminology, see the Model Context Protocol documentation on the modelcontextprotocol.io website.

    With MCP Server Console, you can create MCP servers on an instance and configure the tools that they expose or use a preconfigured Quickstart Server. Tools define which functionality and data a server exposes to clients and the actions that can be performed on an instance by clients. You can create tools based on existing capabilities, such as Now Assist skills.

    Then any AI application, such as Microsoft Copilot or Claude, can call a server from a client using OAuth 2.0 authentication and get a list of available tools. With these tools, employees using MCP clients can prompt the server for information from the instance or to perform an action on the instance, such as to summarize a list of recently closed incidents or cases. You can also use the ServiceNow Model Context Protocol Client to let an AI application on one instance access tools from an MCP server on another instance.

    MCP Server Console users

    User Description
    AI administrator AI administrators can create MCP servers and configure which tools they expose to MCP clients. They also create OAuth inbound integrations on the instance for each client and configure clients with the server and authentication details.

    MCP Server Console workflow

    The following infographic shows the workflow for AI administrators to get started managing MCP servers with MCP Server Console.

    Figure 1. Managing MCP servers with MCP Server Console
    Process for managing MCP servers on a ServiceNow instance and connecting to a server from an MCP client in an AI application. For details, refer to the following description.
    1. As an AI administrator, you identify which functionality on an instance to access from an external MCP client and employee experience.
    2. You can use the preconfigured Quickstart Server or create an MCP server with the appropriate tools to use the desired functionality.

      You can create one or more servers that expose different tools for different use cases, such as for HR or IT workflows, or for different clients.

    3. If needed, you can create additional tools from Now Assist skills and configure which fields are exposed to clients and then add the tools to servers.
    4. You create OAuth inbound integrations for each client to secure access to servers on an instance.
    5. You configure clients to connect to a server using the server and OAuth inbound integration details.

      Then the client calls the server, which validates the OAuth token and responds with the list of tools available for use with the server.

    6. Employees use clients, such as AI agents, to prompt the server for data from the instance or to perform an action on the instance.
    Note:
    With AI Gateway in AI Control Tower, AI administrators can monitor MCP server access and view metrics for servers and their tools. For more information, see .

    MCP Server Console benefits

    Benefit Feature Users
    Integrate with any AI application and MCP client using a standard protocol. Create a Model Context Protocol server AI administrator
    Control which tools and fields are exposed to MCP clients. Create a tool for a Model Context Protocol server AI administrator
    Securely access functionality from a ServiceNow instance in any external employee experience. Configure an MCP client to connect to an MCP server AI administrator

    Quickstart Server in MCP Server Console

    MCP Server Console includes a preconfigured Quickstart Server to help you get started learning about MCP servers and connecting MCP clients to a ServiceNow instance. The Quickstart Server includes tools for looking up and summarizing incident and case records.

    Table 1. Quickstart Server tools
    Name Description
    Case summarization Get a summary of details in a case record generated by Now Assist.
    Incident summarization Get a summary of details in an incident record generated by Now Assist.
    Look up Case Records Look up case records to enable summarizing them with the Case Summarization tool.
    Look up Incident Records Look up incident records to enable summarizing them with Incident summarization tool.

    What to explore next

    To learn more about configuring and using MCP Server Console, see: